51 results about "Gene map" patented technology

The invention discloses a metal mine crushing and grinding process simulation and prediction method and system, and relates to the technical field of grinding control, and the method comprises the steps: collecting whole-size distribution data, ore component data and ore grade, transmitting the data to an edge calculation node for data cleaning, extracting key feature parameters, and generating an ore genetic map vector; the actual whole-size distribution data and the equipment energy consumption data are compared with operation parameters, and when any data exceeds a preset prediction threshold value, a time delay cause and effect graph is constructed, fault equipment is positioned, and an equipment health degree report is output; and according to the equipment health degree report, generating an adversarial sample by adopting a generative adversarial network, injecting the adversarial sample into the digital twinborn model, reconstructing grinding process parameters to complete self-calibration of the digital twinborn model, and updating a pre-stored typical ore sample. The working condition adaptability of the grinding process is improved through a dynamic gene matching mechanism.

The invention relates to the technical field of intelligent vocational ability analysis, and discloses a dynamic planning method for a vocational ability genetic map based on multi-modal data and federal learning. The method comprises the steps that multi-source heterogeneous data in occupational activities is collected, and a multi-modal data set is formed through data cleaning and standardization processing; a graph neural network technology is utilized to construct a correlation topology between capability elements, spatio-temporal context information is fused, a dynamically evolved vocational capability gene map is established, and the accuracy and interpretability of vocational capability analysis are improved. Multi-node cooperative training is realized by adopting a federated learning framework, data privacy security is ensured in combination with a differential privacy technology, and the problem of data islands is solved. A capability evolution path is simulated based on a three-dimensional visualization and digital twinning technology, an occupational development scheme is generated through an intelligent recommendation algorithm, and a real-time feedback optimization mechanism is established. According to the method, dynamic, visual and personalized vocational ability analysis is realized, and accurate decision support is provided for vocational planning.

The invention discloses an online stress monitoring device and method based on Modbus-RTU stress sensing and digital communication, and the method comprises the steps: collecting original stress data and a multi-dimensional environment parameter sequence through stress sensing nodes, constructing an exclusive environment gene map, generating a dynamic compensation model, and carrying out the environment coupling decoupling and self-adaptive correction of the original data; a periodic self-diagnosis process is executed in the monitoring process, signal impedance characteristics and output signal stability are analyzed, and an equipment state fault code is generated and actively uploaded through a Modbus-RTU protocol when abnormity occurs; triggering a cooperative monitoring mechanism based on the corrected stress measurement value, controlling adjacent nodes to enter a high-frequency sampling mode and generating a stress propagation dynamic cloud; meanwhile, a node performance baseline is established, and a gain self-regeneration process is started when performance degradation is detected. Accurate compensation and dynamic correction of stress data are realized, and the environmental adaptability, the operation reliability and the fault early warning capability of a monitoring system are remarkably improved.

The invention relates to the technical field of digital protection and exchange of cultural heritage, in particular to a visual information design optimization method for a non-genetic-cultural genetic map. Through fusion of multi-modal image features and cross-scale stratified analysis, a visual optimization system of a non-genetic-culture genetic map is constructed. RGB, depth and infrared multi-mode images are synchronously collected, and macroscopic, mesoscopic and microscopic multi-scale feature extraction is combined, so that deep association of pattern visual representation and cultural semantics is realized; a pre-training semantic model adaptive to the field and cross-modal correlation degree calculation are adopted, cultural symbols and pattern visual features in a spoken text of an inheritor are effectively fused, and the problem of semantic superficial layer of a traditional method is solved; based on an iterative verification mechanism of dynamic weight adjustment, through quantitative matching of feature attributes and semantic parameters, the consistency of culture genes with different scale features is ensured.

The invention discloses a synthetic lethal prediction method based on non-generality forgetting and low-rank interaction multi-mode adaptive fusion, and relates to the technical field of bioinformatics, computational biology and drug target screening. The method comprises the following steps: firstly, constructing a multi-view gene embedding expression based on a gene graph structure, a hypergraph structure and a knowledge graph; then constructing a difference vector and an interaction vector for any gene pair so as to characterize the difference and potential complementary relationship between the genes; multi-source information fusion is realized by using a deep learning model containing interactive attention, a forgetting gate and a multi-modal fusion mechanism; on this basis, multi-task optimization is carried out through joint classification loss, modal interaction loss and redundancy suppression loss, and optimal discrimination is realized through a dynamic threshold search strategy; and finally, outputting a sorting result of the candidate synthetic lethal gene pairs according to the prediction score. According to the method, the accuracy and generalization ability of synthetic lethal relationship prediction can be effectively improved, and a high-reliability calculation auxiliary tool is provided for anti-cancer drug target screening and gene therapy strategy design.

The invention relates to the field of model design, and provides an aircraft multi-objective optimization design method and system based on semanteme in order to improve the calculation efficiency of multi-objective balance. Firstly, original design parameters and design rules are obtained, obtained data are converted into semantic vectors through a semantic embedding function, and adjacency matrixes are obtained; generating a semantic gene map based on the semantic vector and the adjacent matrix, constructing a comprehensive objective function, and performing optimization solution based on the semantic gene map; and creating a target mapping function, and mapping an optimized result into a specific engineering target based on the target mapping function. By introducing a semantic modeling and cognitive enhancement mechanism, aircraft structure optimization is improved from traditional numerical drive to semantic drive, a prediction and search process is accelerated by using semantic space and cognitive reasoning, and global optimization and traceability are realized in combination with crowd intelligence evolution and a cross-domain hypernetwork; not only are efficiency and robustness improved, but also engineering feasibility and compliance credibility of a design result are ensured.

The invention relates to the field of data security, in particular to a network security intelligent detection method based on big data, and the method comprises the steps: collecting network flow data, a terminal system call sequence and a user operation behavior log, and carrying out the data fusion processing to generate a unified behavior event flow; selecting a key behavior event based on an information entropy threshold value, performing time alignment through a dynamic time warping algorithm, and constructing a behavior gene map containing a communication association gene, an operation sequence gene and a behavior time sequence gene; a dynamic behavior baseline model is established by using unsupervised learning, and gene mutation detection and alarm are realized by calculating the deviation degree of each gene dimension; the detection performance is evaluated based on the false alarm rate, model parameters are optimized through a negative feedback mechanism, and acknowledged attack features are stored in a sharable threat gene feature library through a positive feedback mechanism. According to the method, the detection accuracy is continuously improved through a closed-loop learning mechanism, and a self-adaptive safety protection system with self-optimization capability is constructed.

The invention belongs to the field of disease evolution trajectory prediction in precision medicine, and discloses a Parkinson's disease evolution prediction modeling method based on high-order gene communication tensor. According to the method, firstly, based on an intercellular communication mechanism, a high-order gene module communication tensor is constructed as spatial topological data, so that an information interaction mode between gene modules is described; secondly, a self-adaptive Transform module is designed to extract gene expression features and high-order space topology features at the same time; and finally, integrating multi-view interaction information between the high-order gene module communication tensor and the whole blood transcriptome data through a multi-view collaborative fusion mechanism to realize effective fusion and utilization of features. Experimental results show that compared with a traditional genetic map, the high-order space representation provided by the invention has finer resolution capability, a plurality of evaluation indexes are remarkably improved, and a new technical means is provided for accurate staging of Parkinson's disease.

The invention relates to a structural network-genetic map biological network model for predicting ischemic stroke and a construction method thereof, and the method comprises the steps: extracting and calculating seven multi-scale morphological features and pairwise Pearson correlation coefficients among the features from T1 weighted imaging data and diffusion tensor imaging data; constructing a 308 * 308 morphological similarity network matrix and a brain network module for identifying ischemic stroke neural dysfunction; 1782 sampling points are extracted from the Airy human brain map, and each sampling point comprises expression data of 10185 genes; the method comprises the following steps: mapping space coordinates of AHBA sampling points to a cortex package of a Desikan-Killiany map, carrying out normalization processing to output 308 * 10185 brain region gene-by-gene expression matrixes, and constructing a structural network-gene map biological network model for predicting ischemic stroke by adopting a partial least square regression method and a bootstrap method. Compared with the prior art, the model determines the specific molecular mechanism related to the phenotypic structure change of ischemic stroke injury, and the stroke occurrence probability is predicted according to the specific molecular mechanism.

Provided in the present application are a gene image data correction method and system, and an electronic device and a storage medium. The gene image data correction method comprises: inputting spatial coordinates and a gene expression feature signal value into a probability distribution model, so as to obtain a probability score of a background gene molecule belonging to a target cell; and according to the probability score, determining a cell to which the background gene molecule belongs. In the present application, with a rough understanding of a target region of a target cell, a probability score of a background gene molecule, with a cell to which the background gene molecule belongs being unknown, within a preset correction range belonging to a target cell is calculated, and the cell to which the background gene molecule belongs is determined according to the probability score, thereby reducing situations where errors in gene image data are large due to the diffusion of gene molecules, and increasing the correction efficiency; moreover, the present application does not rely on high-precision cell segmentation results, thereby enhancing the robustness of the correction scheme.

1. Name of the design product: Porcelain cup (Original ore white porcelain cup with school history gene map). 2. Use of the design product: Utensil for tea drinking. 3. Design key points of the design product: The combination of shape and pattern. 4. Picture or photo that best shows the design key points: Perspective view.

The application relates to a cancer driver gene explainable identification method based on trust calibration and prototype learning, and relates to the technical field of biological information identification. A gene graph is constructed by fusing a protein interaction network and gene multi-omics characteristics, and part of nodes are labeled. Label-aware message passing is performed through a trust calibration encoder, the neighborhood is split into a labeled part and a non-labeled part for independent calibration, and node embedding is adaptively fused. An angle margin prototype classifier is used to construct a class prototype on a hypersphere, the decision boundary is expanded, and a prediction result is output. A pivot node self-supervised regularizer is introduced, center nodes are screened from labeled driver genes, positive constraints are applied to neighbor non-labeled nodes, negative penalties are applied to non-neighbors, and a supervised boundary is maintained when non-labeled data is used. Finally, a structured explanation module is used to reuse the internal evidence of the model, a verifiable explanation is provided for prediction, and the unification of high precision and credible explanation is realized.

The invention provides an SNP (Single Nucleotide Polymorphism) individual map construction method based on linkage imbalance, which introduces a weighted edge weight calculation method of a linkage imbalance value and a physical position difference, and innovatively brings a relationship between genetic association strength and a physical distance between SNPs into edge weight calculation; through logarithmic transformation of the physical position difference, the genetic relevance of the SNP pair which is close to the gene map is highlighted, it is ensured that the weight of the edge in the gene map can accurately reflect the biological significance, and the interpretability of the gene map and the biological relevance of data are improved.

The invention discloses a Tujia brocade culture genetic map-based virtual digital human role precise modeling system and method, and relates to the technical field of virtual digital human roles, and the system comprises a data acquisition module, a virtual digital human role creation module, a virtual digital human role analysis module and a feedback judgment module. The method comprises the following steps: establishing a target according to a virtual digital human role uploaded by a user, evaluating a scene adaptation index of a demand virtual digital human role model of the user, expanding culture influence, operating the established demand virtual digital human role model of the user, judging whether the demand virtual digital human role model of the user is adaptive or not, and if yes, executing the operation of the user. If the model is not matched with the scene, regeneration is carried out, the requirement integrating degree of the model and the actual use scene is improved, the problems of abnormal functions or poor experience and the like caused by the fact that the model is not matched with the scene are avoided, the working efficiency is improved, and inheritance and propagation of Tujia brocade culture are promoted.

The invention belongs to the technical field of industrial Internet of Things and intelligent manufacturing, and particularly relates to an intelligent ranking method and system for garment production based on the Internet of Things. The method comprises the following steps: retrieving matched candidate genotypes from a production mode gene map library and analyzing the candidate genotypes into an initial ranking scheme; calculating a personnel-equipment-process collaborative adaptation degree coefficient of each station in the scheme; an optimization objective function fusing the collaborative adaptation degree, the historical environment adaptation degree and the production constraint is constructed, and an optimal ranking scheme is solved and output by adopting an improved genetic algorithm; and dynamically constructing a process flow potential energy field in production execution, and generating and executing a task shunting scheduling instruction according to a potential energy gradient. According to the method, the whole-process intelligent ranking from historical experience reuse and global multi-objective optimization to dynamic real-time scheduling is realized, the technical problems that production scheduling depends on experience, the optimization objective is single and dynamic response is insufficient in the flexible clothing production line are effectively solved, and the production scheduling efficiency, the production line balance rate and the system adaptive capacity are remarkably improved.

The invention provides a gene image data correction method and system, electronic equipment and a storage medium, and the method comprises the steps: determining the gene molecule density of a target cell according to the number of molecules and an initial contour area; determining the density of the background gene molecules according to the number of the background gene molecules and the area of the region; and determining cells to which the background gene molecules belong according to the gene molecule density and the background gene molecule density. According to the method, the gene molecule density of the target cell and the background gene molecule density are compared by utilizing the cell characteristic equivalent to the gene molecule density, and the cell to which the background gene molecule belongs is determined according to the gene molecule density and the background gene molecule density, so that the efficiency of correcting the gene molecule in the target cell is greatly improved; meanwhile, the accuracy of correcting the gene molecules in the target cells is also improved.

The application discloses a virtual digital human role precise modeling system and method based on Tujia brocade culture gene map, relates to the technical field of virtual digital human roles, and comprises a data acquisition module, a virtual digital human role creation module, a virtual digital human role analysis module and a feedback judgment module.According to a virtual digital human role creation target uploaded by a user, the scene adaptation index of a virtual digital human role model required by the user is evaluated, the cultural influence is expanded, the virtual digital human role model required by the user is run, and it is judged whether the virtual digital human role model required by the user is adapted.If not, the virtual digital human role model is regenerated, the requirement matching degree of the model and the actual use scene is improved, the problems of function abnormity or poor experience caused by the mismatch between the model and the scene are avoided, the work efficiency is improved, and the inheritance and spread of the Tujia brocade culture are promoted.

The invention provides a spatial transcriptome data clustering method based on modal conflict modulation, and relates to the technical field of biological information, and the method comprises the steps: carrying out the preprocessing of original spatial transcriptome data, and constructing a spatial diagram and a gene diagram; performing cross propagation learning of gene features and spatial features by using a graph convolutional network and taking the gene expression feature matrix, the spatial graph and the gene graph as input; in the training process, random masking is carried out on the space diagram, the gene is embedded and projected to a unit hypersphere, the reconstruction probability of masked connection is calculated based on the projected features, and a reconstruction loss function is constructed by using Jensen-Shannon divergence; and combining the reconstruction loss, the gene expression reconstruction loss and the spatial feature reconstruction loss to construct a total loss function training graph convolutional network. According to the technical scheme, the problem that the node distinguishing capability in the space transcriptomics data is weak is solved.

The application provides a transient working condition multi-parameter collaborative calibration method and system of a hybrid internal combustion engine, and the method comprises the following steps: acquiring a data stream in an on-board diagnostic system, and screening feature information of seven key dimensions from the data stream; creating a gene map matching engine, and inputting the feature information of the seven key dimensions into the gene map matching engine; comparing the feature information of the seven key dimensions with pre-stored working conditions in the gene map matching engine, obtaining an optimal working condition, and outputting a corresponding basic parameter package; combining knock energy spectrum characteristics and oxygen sensor offset, and performing matrix operation to optimize the basic parameter package, and obtaining a corrected parameter package; and performing boundary control on an ignition angle based on operating parameters of the internal combustion engine, and using the boundary-controlled ignition angle to constrain the ignition angle in the operation process of the internal combustion engine. The application can dynamically correct each parameter of the internal combustion engine.

This application aims at the privacy protection and security protection of industrial information-physical systems, and proposes a multi-level identity authentication method based on time-frequency domain gene feature extraction and fusion portrait. First, based on the acquired time series signal, an autoencoding mathematical representation model with the multi-order moment feature of the data as the basic function and a multi-scale representation model with wavelet as the basic function are established respectively; secondly, based on the autoencoding representation and multi-scale representation of real-time data, multi-granularity features of the time domain and frequency domain are extracted respectively; then, the extracted multi-granularity features are used to establish a multi-level image representation based on the time-frequency gene fusion portrait; finally, the multi-level portrait representation is subjected to multi-level matching authentication with images in the standard gene image library. The identity authentication method proposed in this application ensures the integrity and validity of the data and significantly improves the authentication speed.

The invention provides a method, a device and equipment for determining a setting value of an electric power low-voltage protection system, and the method comprises the steps: generating an equipment state sequence according to the operation state data of each low-voltage protection equipment, and enabling the equipment state sequence to represent the health states of the low-voltage protection equipment under different time sequences; compressing the equipment state sequence code to obtain a digital gene map code; matching the digital gene map code with the topological data of the power distribution network to obtain a code-topological mapping relation; determining a current-time characteristic requirement of each low-voltage protection device and an initial setting value of each low-voltage protection device according to the coding-topology mapping relation, and enabling the initial setting value to meet the current-time characteristic requirement; and performing simulation iteration adjustment on the setting value through a power distribution twinborn model. The coding-topology mapping relation can accurately reflect the personalized characteristics of the low-voltage protection equipment, so that the initial setting value of each piece of low-voltage protection equipment is determined, the actual operation condition of the equipment is better met, and the setting value scheme is more accurate.

The invention discloses a multi-gene interaction network prediction method and system based on a graph neural network. The method comprises the following steps: S1, acquiring multi-source biological data; s2, carrying out pretreatment; s3, constructing a gene map; s4, fusing the edge weight matrix and the node feature matrix in the gene map through a dynamic attention mechanism, and outputting a refined feature set; s5, acquiring an optimal hyper-parameter set by using a Bayesian optimization algorithm; s6, based on the gene map and the optimal hyper-parameter set, training the attention enhancement map neural network to obtain a multi-gene interaction network prediction model; and S7, predicting the interaction relationship of the unknown gene pair by using the multi-gene interaction network prediction model, and outputting a result. According to the method, the gene map is constructed through multi-source data fusion, the gene association information is enriched, the multi-head attention map neural network is introduced to automatically learn the interaction weight, the hyper-parameters are dynamically adjusted in combination with Bayesian optimization, and the prediction accuracy and model universality of the multi-gene interaction network are improved.

The invention provides a gene image data correction method and system, electronic equipment and a storage medium. The gene image data correction method comprises the following steps: inputting a space coordinate and a gene expression characteristic signal value into a probability distribution model to obtain a probability score of a target cell to which a background gene molecule belongs; and determining cells to which the background gene molecules belong according to the probability score. On the premise of roughly knowing the target area of the target cell, the probability score of the background gene molecule belonging to the unknown belonging cell in the preset correction range belongs to the target cell is calculated, and the belonging cell of the background gene molecule is determined according to the probability score. The situation of large gene image data error caused by gene molecule diffusion is reduced, and the correction efficiency is improved; and meanwhile, the method does not depend on a high-precision cell segmentation result, so that the robustness of a correction scheme is enhanced.

This invention belongs to the field of plant gene map-based cloning and molecular breeding, and relates to the application of the maize gene BRR1 and its functional site in regulating harvest index and yield traits. Through QTL mapping and fine mapping of a maize-Kesury grass population, this invention identified the major-effect QTL-HI1 regulating the harvest index and its key gene BRR1, and discovered that its upstream 9.1 kb insert is an enhancer with H3K27ac modification, which can physically interact with the BRR1 promoter and significantly upregulate gene expression. Knockout of BRR1 leads to a decrease in harvest index, biomass, and yield, and delayed flowering; overexpression of BRR1 increases harvest index and yield by 10–16%. This gene and its functional site are subject to strong selection during domestication and breeding, and can be used through transgenic technology or marker-assisted selection to achieve synergistic improvement of maize harvest index, yield, and flowering time, providing a new approach for high-yield molecular design breeding.

The invention discloses a barley stalk and spike epidermal wax gene HvCer1 as well as an encoding protein and application thereof, and belongs to the technical field of gene engineering. The nucleotide sequence of the barley HvCer1 gene is as shown in SEQ ID NO. 1. According to the invention, map-based cloning is carried out on the barley HvCer1 gene, functional verification is carried out on the gene in combination with a CRISPR-Cas9 gene editing technology, and it is found that the HvCer1 gene regulates wax synthesis of barley stalks and ears. The invention provides a theoretical basis and a new gene for barley epidermis wax synthesis.

The application discloses a kind of metal mine broken grinding process simulation prediction method and system, it is related to grinding control technical field, including, collection full particle size distribution data, ore composition data and ore grade, transmission to edge computing node carries out data cleaning, extracts key feature parameters, generates ore gene atlas vector;Actual full particle size distribution data and equipment energy consumption data are compared with operating parameters, when any data exceeds preset prediction threshold, construct time-delay causal diagram, locate fault equipment, output equipment health degree report;According to equipment health degree report, using generative adversarial network generates adversarial sample injection digital twin model, reconstructs broken grinding process parameters to complete digital twin model self-calibration, and update pre-stored typical ore sample.The application improves the working condition adaptability of broken grinding process by dynamic gene matching mechanism.

The invention provides an educational resource sharing method and system for a big data platform, and relates to the technical field of educational resource data processing and sharing, and the method comprises the steps: constructing a dynamic resource genetic map which is formed by the vectorization fusion of static genes and dynamic performance characteristics of educational resources; matching the dynamic learning model of the user with the dynamic resource genetic map to generate a resource recommendation sequence; carrying out collaborative optimization on the dynamic resource gene map and a dynamic learning model of the user according to feedback data of the user on the resource recommendation sequence based on a reinforcement learning model; based on the optimized dynamic resource gene map and a dynamic learning model of the user, constructing a systematic learning path for the user, and realizing resource sharing according to the systematic learning path; the intelligent recommendation capability and the self-adaptive learning support of the system are enhanced, and the accuracy, the dynamism and the user experience optimization of educational resource sharing are promoted.

The application discloses a whole genome prediction parallel computing and data visualization analysis system and relates to the technical field of gene image data analysis. The system converts whole genome data into a genome heat map, a genome variation map and a gene structure diagram through parallel computing. Through an image processing algorithm, the system accurately extracts gene expression differences, gene variation characteristics and gene region distribution density in the genome image, and generates an expression difference index, a variation distribution map and a gene density index. According to a machine learning model, the system predicts gene expression trends, variation hot spot evolution and functional region distribution, and generates a genome prediction map. Finally, the system displays and analyzes the analysis results through multiple levels of graphics, helps researchers to intuitively identify the expression changes, variation hot spots and region distribution characteristics of genes, and improves the computing efficiency of large-scale genome data processing. Meanwhile, through multi-level visualization display, the system enhances the intuitiveness and interpretability of data analysis.

This application relates to the technical field of text plagiarism detection, and discloses a text plagiarism detection method combining gene mapping and zero-knowledge proof. The method includes: segmenting the text into plot exons and transition introns, extracting structural features through dependency parsing, decomposing it into three-stage plot units, constructing a directed acyclic graph with plot units as nodes and logical dependencies as edges, and assigning dynamic weights; calculating structural and semantic similarity using graph neural networks and BERT models respectively, analyzing narrative logic similarity, and weighted fusion to obtain a comprehensive similarity; hashing the text gene map segments and uploading it to the blockchain to form a four-layer association chain, recording structural changes through smart contracts, and designing a zero-knowledge proof verification mechanism; setting multi-level judgment thresholds, combining multi-dimensional similarity to perform suspected content and plot plagiarism judgments, and updating the model and threshold strategy based on user feedback. This application can meet the requirements of accurate, secure, and flexible text content structure plagiarism judgment.

The invention discloses an information stealing risk monitoring method and system based on big data, and the method comprises the following steps: data ecological perception and risk potential energy modeling: carrying out the automatic scanning of enterprise total data assets, generating a data fingerprint, and constructing a data gene map; based on the data genetic map, calculating three-dimensional risk potential energy of each data object, the three-dimensional risk potential energy including intrinsic potential energy quantified data intrinsic value, environmental potential energy quantified data exposure degree, association strength of associated potential energy quantified data with other high-value data, and associated potential energy quantified data exposure degree with other high-value data; according to the method, the data value and the exposure degree are quantified through inherent, environmental and associated three-dimensional risk potential energy, the potential energy is adjusted in real time in combination with event driving, data risk changes can be dynamically matched, risk misjudgment or omission caused by static evaluation is avoided, and risk perception better fits an actual business scene.